Performance estimation of a thin-film photovoltaic plant based on an Artificial Neural Network model

Giorgio Graditi, Sergio Ferlito, Giovanna Adinolfi, Giuseppe Marco Tina, Cristina Ventura

Research output: Contribution to conferencePaper

8 Citations (Scopus)

Abstract

An Artificial Neural Network (ANN) approach is used to estimate power production yield by a 1 kWp experimental micro-morph silicon modules plant located at ENEA Portici Research Centre, in Italy South region. A large dataset consisting of data, measured every five minutes and acquired from 2006 to 2012, is used for the training/test of the ANN. First, AC power production evaluation is obtained from single-hidden layer Multi-Layer Perceptron (MPL) Neural Network with two inputs consisting in ambient temperature and solar global radiation. In order to improve the approximation of the AC power, the clear sky solar radiation is then added as input of the ANN. Experimental data are reported to demonstrate the feasibility and the potentiality of the adopted solutions. © 2014 IEEE.
Original languageEnglish
DOIs
Publication statusPublished - 2014
Event2014 5th International Renewable Energy Congress, IREC 2014 - , Tunisia
Duration: 1 Jan 2014 → …

Conference

Conference2014 5th International Renewable Energy Congress, IREC 2014
CountryTunisia
Period1/1/14 → …

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Renewable Energy, Sustainability and the Environment

Cite this

Graditi, G., Ferlito, S., Adinolfi, G., Tina, G. M., & Ventura, C. (2014). Performance estimation of a thin-film photovoltaic plant based on an Artificial Neural Network model. Paper presented at 2014 5th International Renewable Energy Congress, IREC 2014, Tunisia. https://doi.org/10.1109/IREC.2014.6826954